def parse_alignments (file_adr):
##
# @brief Read the COORD file 'file_adr' to fill and return a table containing all the alignments between two different contigs.
# @param file_adr file containing the alignments between two assemblies (MUMmer COORD file)
# @return a table containing all the alignments between two different contigs
global all_alignments,aln_threshold,ctg_threshold,ctg_threshold,cov_threshold
all_alignments = [x for x in mummerParser.parse_mummerFile(file_adr) if x['TAGQ']!=x['TAGR']]
alignments=[]
contigs = {}
contigs_included_in_other = []
for aln in all_alignments:
# Build mapping
for c in ["R", "Q"] :
if aln["TAG"+c] not in contigs :
contigs[aln["TAG"+c]] = aln["LEN"+c]
if aln['TAGQ']==aln['TAGR']:
continue
# We know that the two alignments are different,
# Do we have contigs completely included (AKA "covered") by another ?
if ((aln["COVR"] > cov_threshold) or ((aln["LENR"] - aln["LEN1"]) < ctg_threshold)):
contigs_included_in_other.append(aln["TAGR"])
elif ((aln["COVQ"] > cov_threshold) or ((aln["LENQ"] - aln["LEN2"]) < ctg_threshold)):
contigs_included_in_other.append(aln["TAGQ"])
if (aln_pass_thresholds(aln)) and (not reverse_is_in_alignments(aln, alignments)) and (is_extremal(aln)):
alignments.append(aln)
contigs_included_in_other=list(set(contigs_included_in_other))
logger.debug("list of contigs %s\n included in others:%s ",str(contigs),contigs_included_in_other)
return alignments, contigs, contigs_included_in_other
def main(argv=None):
parser=argparse.ArgumentParser(description="Pipe out the alignments in CSV format")
parser.add_argument('-e',dest="extremal_only",action="store_true",help="Only keep extremal alignments")
parser.add_argument('-k',dest="florence_selection",action="store_true",help="Remove alignments not satisfying Florence criteria")
parser.add_argument('infile', nargs='?', type=argparse.FileType('r'), default=sys.stdin)
parser.add_argument('-o', nargs='?', type=argparse.FileType('w'), default=sys.stdout,dest="outfile")
args=parser.parse_args()
alignments=mummerParser.parse_mummerFile(args.infile)
# Get col names
a=alignments[0]
items = a.items()
items.sort(key=itemgetter(0))
print>>args.outfile, "\t".join(map(str,[x[0] for x in items]))
for a in alignments:
if args.extremal_only:
if not is_extremal(a):
continue
if args.florence_selection:
if not is_kept(a):
continue
items = a.items()
items.sort(key=itemgetter(0))
print>>args.outfile, "\t".join(map(str,[x[1] for x in items]))
def main(argv=None):
parser=argparse.ArgumentParser(description="Pipe out the alignments involving or excluding provided contigs ID")
parser.add_argument('-e',dest="inverse_match",action="store_true",help="Inverse the criterion, filter out any conting in CONTIGID list (not implemented yet)")
parser.add_argument('-r',dest="use_re",action="store_true",help="Consider CONTIGID as python regexp (not implemented yet)")
parser.add_argument('-s',dest="remove_self",action="store_true",help="remove self alignments")
parser.add_argument('-p',dest="pretty",action="store_true",help="Pretty print")
parser.add_argument('-v',dest="verbose",action="store_true",help="Verbose output")
parser.add_argument('infile', nargs='?', type=argparse.FileType('r'), default=sys.stdin)
parser.add_argument('-o', nargs='?', type=argparse.FileType('w'), default=sys.stdout,dest="outfile")
parser.add_argument('CONTIGS',action='append',nargs="+",help='List of CONTIGS to keep. Use "*" to keep them all')
args=parser.parse_args()
contig_ids=args.CONTIGS[0]
alignments=mummerParser.parse_mummerFile(args.infile)
kept_alignments=[]
for a in alignments:
if "*" in contig_ids and ((args.remove_self and a['TAGQ']!=a['TAGR'])or not args.remove_self):
kept_alignments.append(a)
if a['TAGQ'] in contig_ids and a['TAGR'] in contig_ids:
kept_alignments.append(a)
elif args.verbose:
print >>args.outfile,"Skipped",a
for a in kept_alignments:
mummerParser.print_alignment(a,args.outfile,args.pretty)
def main(argv=None):
parser = argparse.ArgumentParser(
description=
"Pipe out the alignments involving or excluding provided contigs ID")
parser.add_argument(
'-e',
dest="inverse_match",
action="store_true",
help=
"Inverse the criterion, filter out any conting in CONTIGID list (not implemented yet)"
)
parser.add_argument(
'-r',
dest="use_re",
action="store_true",
help="Consider CONTIGID as python regexp (not implemented yet)")
parser.add_argument('-s',
dest="remove_self",
action="store_true",
help="remove self alignments")
parser.add_argument('-p',
dest="pretty",
action="store_true",
help="Pretty print")
parser.add_argument('-v',
dest="verbose",
action="store_true",
help="Verbose output")
parser.add_argument('infile',
nargs='?',
type=argparse.FileType('r'),
default=sys.stdin)
parser.add_argument('-o',
nargs='?',
type=argparse.FileType('w'),
default=sys.stdout,
dest="outfile")
parser.add_argument(
'CONTIGS',
action='append',
nargs="+",
help='List of CONTIGS to keep. Use "*" to keep them all')
args = parser.parse_args()
contig_ids = args.CONTIGS[0]
alignments = mummerParser.parse_mummerFile(args.infile)
kept_alignments = []
for a in alignments:
if "*" in contig_ids and ((args.remove_self and a['TAGQ'] != a['TAGR'])
or not args.remove_self):
kept_alignments.append(a)
if a['TAGQ'] in contig_ids and a['TAGR'] in contig_ids:
kept_alignments.append(a)
elif args.verbose:
print >> args.outfile, "Skipped", a
for a in kept_alignments:
mummerParser.print_alignment(a, args.outfile, args.pretty)
def main(argv=None):
parser = argparse.ArgumentParser(
description="Pipe out the alignments in CSV format")
parser.add_argument('-e',
dest="extremal_only",
action="store_true",
help="Only keep extremal alignments")
parser.add_argument(
'-k',
dest="florence_selection",
action="store_true",
help="Remove alignments not satisfying Florence criteria")
parser.add_argument('infile',
nargs='?',
type=argparse.FileType('r'),
default=sys.stdin)
parser.add_argument('-o',
nargs='?',
type=argparse.FileType('w'),
default=sys.stdout,
dest="outfile")
args = parser.parse_args()
alignments = mummerParser.parse_mummerFile(args.infile)
# Get col names
a = alignments[0]
items = a.items()
items.sort(key=itemgetter(0))
print >> args.outfile, "\t".join(map(str, [x[0] for x in items]))
for a in alignments:
if args.extremal_only:
if not is_extremal(a):
continue
if args.florence_selection:
if not is_kept(a):
continue
items = a.items()
items.sort(key=itemgetter(0))
print >> args.outfile, "\t".join(map(str, [x[1] for x in items]))
def main():
parser=argparse.ArgumentParser(description="Display nucmer alignments in ASCII")
parser.add_argument('-w',dest="max_width",action="store",type=int,default=110,help="Width of text output")
parser.add_argument('infile', nargs='?', type=argparse.FileType('r'), default=sys.stdin,help="Nucmer coords file")
args=parser.parse_args()
alignments=mummerParser.parse_mummerFile(args.infile)
# Filter out self alignments
alignments=[x for x in alignments if x['TAGQ']!=x['TAGR']]
print "Found",len(alignments)
if len(alignments)<1:
sys.exit(0)
if len(alignments)>len(align_keys):
alignments.sort(key=lambda x:x['LEN2'],reverse=True)
alignments=alignments[:len(align_keys)-3]
alignments.sort(key=lambda x:x['S1'])
print "Filter down to",len(alignments)
print_aligned_contigs(alignments,max_width=args.max_width)